update

toolbox/torchaudio/models/vad/cnn_vad/modeling_cnn_vad.py

@@ -201,6 +201,10 @@ class CNNVadModel(nn.Module):
             raise AssertionError("Input signals must have the same shape")
         noise = noisy - clean
 
+        print(f"lsnr: {lsnr.shape}")
+        print(f"clean: {clean.shape}")
+        print(f"noisy: {noisy.shape}")
+
         if clean.dim() == 2:
             clean = torch.unsqueeze(clean, dim=1)
         if noise.dim() == 2:
@@ -223,6 +227,9 @@ class CNNVadModel(nn.Module):
         lsnr_gth = self.lsnr_fn.forward(stft_clean, stft_noise)
         # lsnr_gth shape: [b, t]
 
+        print(f"lsnr: {lsnr.shape}")
+        print(f"lsnr_gth: {lsnr_gth.shape}")
+
         loss = F.mse_loss(lsnr, lsnr_gth)
         return loss